© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11141
    Prev
    Next
    INDEX
    Explanations

    details about duration and format of media, particularly focusing on minutes and structured timing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text describing time length or duration

    np_acts-logits-general · gemini-2.0-flash

    length and duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enllaços
    -0.37
     confianza
    -0.32
     corrupción
    -0.32
     Seguridad
    -0.30
     autoridad
    -0.29
    bezpe
    -0.28
     acreditar
    -0.28
     reaccion
    -0.27
     Geistes
    -0.27
     cooperación
    -0.27
    POSITIVE LOGITS
    awtextra
    0.74
     autorytatywna
    0.73
     length
    0.71
     noDo
    0.71
    BeginContext
    0.71
    twimg
    0.69
    istoitu
    0.68
     lenght
    0.66
    ength
    0.66
     Length
    0.64
    Activations Density 0.451%

    No Known Activations